mlsanityData to 14 Oct 2026

PatchNets: Patch-Based Generalizable Deep Implicit 3D Shape Representations

arXiv 2008.01639 ↗First posted 4 Aug 2020cs.CV cs.GRcited by 81

Not on the map. Why?

Abstract (arXiv)

Implicit surface representations, such as signed-distance functions, combined with deep learning have led to impressive models which can represent detailed shapes of objects with arbitrary topology. Since a continuous function is learned, the reconstructions can also be extracted at any arbitrary resolution. However, large datasets such as ShapeNet are required to train such models. In this paper, we present a new mid-level patch-based surface representation. At the level of patches, objects across different categories share similarities, which leads to more generalizable models. We then introduce a novel method to learn this patch-based representation in a canonical space, such that it is as object-agnostic as possible. We show that our representation trained on one category of objects from ShapeNet can also well represent detailed shapes from any other category. In addition, it can be trained using much fewer shapes, compared to existing approaches. We show several applications of our new representation, including shape interpolation and partial point cloud completion. Due to explicit control over positions, orientations and scales of patches, our representation is also more controllable compared to object-level representations, which enables us to deform encoded shapes non-rigidly.

Key facts. Cited by 81 papers in the map (data through 14 Oct 2026). First posted on arXiv 4 Aug 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 18; 2022: 23; 2023: 23; 2024: 13; 2025: 2; 2026: 2.

81 papers.

Sort:

By area:

  1. 2021Neural Fields in Visual Computing and Beyondcited by 540
  2. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  3. 2021Advances in Neural Renderingcited by 365
  4. 2021A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representationcited by 114
  5. 2022POCO: Point Convolution for Surface Reconstructioncited by 92
  6. 2021FoV-NeRF: Foveated Neural Radiance Fields for Virtual Realitycited by 79
  7. 2021SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elementscited by 72
  8. 2022Towards Implicit Text-Guided 3D Shape Generationcited by 68
  9. 2022LISA: Learning Implicit Shape and Appearance of Handscited by 63
  10. 2024Advances in 3D Generation: A Surveycited by 63
  11. 2021Geometry-Consistent Neural Shape Representation with Implicit Displacement Fieldscited by 60
  12. 2022Reconstructing Surfaces for Sparse Point Clouds with On-Surface Priorscited by 60
38 more
  1. 2021SA-ConvONet: Sign-Agnostic Optimization of Convolutional Occupancy Networkscited by 59
  2. 2022Surface Reconstruction from Point Clouds by Learning Predictive Context Priorscited by 54
  3. 2024CViT: Continuous Vision Transformer for Operator Learningcited by 51
  4. 2022CAP-UDF: Learning Unsigned Distance Functions Progressively from Raw Point Clouds with Consistency-Aware Field Optimizationcited by 47
  5. 2021Dynamic Surface Function Networks for Clothed Human Bodiescited by 44
  6. 2022Learning Deep Implicit Functions for 3D Shapes with Dynamic Code Cloudscited by 42
  7. 2022Surface Reconstruction from Point Clouds: A Survey and a Benchmarkcited by 41
  8. 2023Towards Better Gradient Consistency for Neural Signed Distance Functions via Level Set Alignmentcited by 39
  9. 2022Topology-Preserving Shape Reconstruction and Registration via Neural Diffeomorphic Flowcited by 38
  10. 2022GenSDF: Two-Stage Learning of Generalizable Signed Distance Functionscited by 30
  11. 2024Motion2VecSets: 4D Latent Vector Set Diffusion for Non-rigid Shape Reconstruction and Trackingcited by 29
  12. 2023Unsupervised Inference of Signed Distance Functions from Single Sparse Point Clouds without Learning Priorscited by 28
  13. 2022SE(3)-Equivariant Attention Networks for Shape Reconstruction in Function Spacecited by 27
  14. 2022Neural Shape Deformation Priorscited by 27
  15. 2023Learning Signed Distance Functions from Noisy 3D Point Clouds via Noise to Noise Mappingcited by 27
  16. 2021Unsupervised Learning of Fine Structure Generation for 3D Point Clouds by 2D Projection Matchingcited by 26
  17. 2022Few 'Zero Level Set'-Shot Learning of Shape Signed Distance Functions in Feature Spacecited by 22
  18. 2022PatchComplete: Learning Multi-Resolution Patch Priors for 3D Shape Completion on Unseen Categoriescited by 21
  19. 2022Latent Partition Implicit with Surface Codes for 3D Representationcited by 21
  20. 2022PRIF: Primary Ray-based Implicit Functioncited by 17
  21. 2021Fully Understanding Generic Objects: Modeling, Segmentation, and Reconstructioncited by 16
  22. 2023RayMVSNet++: Learning Ray-based 1D Implicit Fields for Accurate Multi-View Stereocited by 15
  23. 2024Unsupervised Occupancy Learning from Sparse Point Cloudcited by 15
  24. 2024Fast Learning of Signed Distance Functions from Noisy Point Clouds via Noise to Noise Mappingcited by 15
  25. 2023Neural Point-based Volumetric Avatar: Surface-guided Neural Points for Efficient and Photorealistic Volumetric Head Avatarcited by 14
  26. 2021AIR-Nets: An Attention-Based Framework for Locally Conditioned Implicit Representationscited by 13
  27. 2023Partition Speeds Up Learning Implicit Neural Representations Based on Exponential-Increase Hypothesiscited by 13
  28. 2022An Implicit Parametric Morphable Dental Modelcited by 12
  29. 2023Mixing-Denoising Generalizable Occupancy Networkscited by 12
  30. 2023GridPull: Towards Scalability in Learning Implicit Representations from 3D Point Cloudscited by 11
  31. 20213D Shapes Local Geometry Codes Learning with SDFcited by 10
  32. 2023Shape of my heart: Cardiac models through learned signed distance functionscited by 10
  33. 2023Robustifying Generalizable Implicit Shape Networks with a Tunable Non-Parametric Modelcited by 10
  34. 2021Learning and Meshing from Deep Implicit Surface Networks Using an Efficient Implementation of Analytic Marchingcited by 8
  35. 2021Object Wake-up: 3D Object Rigging from a Single Imagecited by 8
  36. 2023Neural Processing of Tri-Plane Hybrid Neural Fieldscited by 8
  37. 2023Diffusion Shape Prior for Wrinkle-Accurate Cloth Registrationcited by 8
  38. 2023NAISR: A 3D Neural Additive Model for Interpretable Shape Representationcited by 7

50 most cited of 81 All 81 (JSON)